NVIDIA A10 PCIe vs AMD Radeon Pro W6900X
GPU · Specs Compare
Graphics Card
Release Date
Apr 2021
Aug 2021
Generation
Tesla
Radeon Pro Mac
Type
Professional
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
885 MHz
1825 MHz
Boost Clock
1695 MHz
2150 MHz
Memory Clock
1563 MHz
2000 MHz
Memory
Memory Size
24GB
32GB
Memory Type
GDDR6
GDDR6
Memory Bus
384bit
256bit
Bandwidth
600.2GB/s
512.0GB/s
Render Config
SM Count
72
—
Shading Units
9216
5120
TMUs
288
320
ROPs
96
128
Tensor Cores
288
—
RT Cores
72
80
L1 Cache
128 KB (per SM)
128 KB per Array
L2 Cache
6 MB
4 MB
Compute Units
—
80
L3 Cache
—
128 MB
Theoretical Performance
Pixel Rate
162.7 GPixel/s
275.2 GPixel/s
Texture Rate
488.2 GTexel/s
688.0 GTexel/s
FP16 (half)
31.24 TFLOPS
44.03 TFLOPS
FP32 (float)
31.24 TFLOPS
22.02 TFLOPS
FP64 (double)
976.3 GFLOPS
1376 GFLOPS
Graphics Processor
GPU Name
GA102
Navi 21
GPU Variant
GA102-890-A1
Navi 21 Pro-XTA
Architecture
Ampere
RDNA 2.0
Foundry
Samsung
TSMC
Process Size
8 nm
7 nm
Transistors
28.3 billion
26.8 billion
Die Size
628 mm²
520 mm²
Board Design
TDP
150W
300W
Suggested PSU
450 W
700 W
Outputs
No outputs
1x HDMI 2.14x Thunderbolt
Power Connectors
1x 8-pin
None
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.3
1.3
CUDA
8.6
—
Shader Model
6.6
6.5
▲ Specs Compare
Data sourced from official specifications and benchmark tests.